Method for ascertaining potential trajectories when controlling a robot device

Abstract

A method for controlling a robot device. The method includes: ascertaining potential trajectories of an object in the surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each of them, a weighting factor assigned thereto; ascertaining weighted similarity values by ascertaining a weighted similarity value for each of the potential trajectories, including: ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to at least one similarity metric, and ascertaining the weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory; adapting the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced sum of the plurality of weighted similarity values.

1 - 10 . (canceled) 
     
     
         11 . A method for controlling a robot device, the method comprising the following steps:
 ascertaining a plurality of potential trajectories of an object in a surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each potential trajectory of the one or more potential trajectories, a weighting factor assigned to the trajectory;   ascertaining a plurality of weighted similarity values by ascertaining a respective weighted similarity value for each potential trajectory of the plurality of potential trajectories, wherein the ascertaining of the respective weighted similarity value for a potential trajectory includes:
 ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to one or more similarity metrics, and 
 ascertaining the respective weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory; 
   summing the plurality of weighted similarity values to produce an error value;   adapting the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced error value;   generating control parameters for controlling the robot device using the adapted set of proposed trajectories; and   controlling the robot device according to the control parameters.   
     
     
         12 . The method according to  claim 11 , wherein:
 each machine learning model of the one or more machine learning models includes a Bayesian neural network; and/or   the weighting factor assigned to a potential trajectory of the one or more potential trajectories represents an uncertainty of the potential trajectory.   
     
     
         13 . The method according to  claim 11 , wherein the plurality of trajectories is ascertained by ascertaining a plurality of trajectories using exactly one machine learning model. 
     
     
         14 . The method according to  claim 11 , wherein the one or more similarity metrics include a minimum average distance error between the potential trajectory and the set of proposed trajectories. 
     
     
         15 . The method according to  claim 11 , wherein the robot device is an at least partially automated vehicle, wherein the object is another road user, and wherein the one or more similarity metrics include a metric that increases the similarity value when the proposed trajectory of the set of proposed trajectories is off-road. 
     
     
         16 . The method according to  claim 11 , wherein the proposed trajectories of the set of proposed trajectories are selected as a subset from the plurality of potential trajectories. 
     
     
         17 . A control device configured to control a robot device, the control device configured to:
 ascertain a plurality of potential trajectories of an object in a surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each potential trajectory of the one or more potential trajectories, a weighting factor assigned to the trajectory;   ascertain a plurality of weighted similarity values by ascertaining a respective weighted similarity value for each potential trajectory of the plurality of potential trajectories, wherein the ascertaining of the respective weighted similarity value for a potential trajectory includes:
 ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to one or more similarity metrics, and 
 ascertaining the respective weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory; 
   sum the plurality of weighted similarity values to produce an error value;   adapt the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced error value;   generate control parameters for controlling the robot device using the adapted set of proposed trajectories; and   control the robot device according to the control parameters.   
     
     
         18 . A robot device, comprising:
 a control device configured to control the robot device, the control device configured to:
 ascertain a plurality of potential trajectories of an object in a surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each potential trajectory of the one or more potential trajectories, a weighting factor assigned to the trajectory; 
 ascertain a plurality of weighted similarity values by ascertaining a respective weighted similarity value for each potential trajectory of the plurality of potential trajectories, wherein the ascertaining of the respective weighted similarity value for a potential trajectory includes:
 ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to one or more similarity metrics, and 
 ascertaining the respective weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory; 
 
 sum the plurality of weighted similarity values to produce an error value; 
 adapt the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced error value; 
 generate control parameters for controlling the robot device using the adapted set of proposed trajectories; and 
 control the robot device according to the control parameters. 
   
     
     
         19 . A non-transitory computer-readable medium in which is stored commands for controlling a robot device, the command, when executed by a processor, causing the processor to perform the following steps:
 ascertaining a plurality of potential trajectories of an object in a surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each potential trajectory of the one or more potential trajectories, a weighting factor assigned to the trajectory;   ascertaining a plurality of weighted similarity values by ascertaining a respective weighted similarity value for each potential trajectory of the plurality of potential trajectories, wherein the ascertaining of the respective weighted similarity value for a potential trajectory includes:
 ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to one or more similarity metrics, and 
 ascertaining the respective weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory; 
   summing the plurality of weighted similarity values to produce an error value;   adapting the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced error value;   generating control parameters for controlling the robot device using the adapted set of proposed trajectories; and   controlling the robot device according to the control parameters.